The amount of computing resources put into place with a grid architecture can be enormous," said Jonathan Eunice, principal I.T. adviser for Illuminata. "Companies get to add the equivalent of a couple thousands PCs and that added horsepower that they do not have to pay for." - Complete article at: http://www.toptechnews.com/story.xhtml?story_id=40364
Thursday, December 29, 2005
What do you need to know to build a storage grid based on open standards? What current technologies can you apply today, and what's coming in the future? In this article, a storage expert takes you on a guided tour through the established standards, the emerging standards, and the standards-related activities relevant to grid storage - Read more at: http://www-128.ibm.com/developerworks/grid/library/gr-storstan/
Saturday, December 17, 2005
Alchemi (http://www.alchemi.net/) is an "open source" software framework that allows you to painlessly aggregate the computing power of networked machines into a virtual supercomputer (computational grid) and to develop applications to run on enterprise grids. It has been developed at the GRIDS Laboratory within the Department of Computer Science and Software Engineering at the University of Melbourne, as part of the Gridbus project (http://www.gridbus.org). The development of Alchemi is partially sponsored by the Australian Research Council (ARC) and Microsoft (via academic support program in Australia). Most importantly, it is also supported by many other volunteers and community of developers through SourceForge: http://sourceforge.net/projects
See more details at:
Saturday, December 10, 2005
It said that Singapore is believed to be among the pioneers in the world to extend grid computing beyond research institutes.
See complete story at:
Singapore National Grid Website: http://www.ngp.org.sg/
I am talking about Grid 2005, this year's International Workshop on Grid Computing in Seattle, just before this year's Supercomputing. In its sixth year, this year's Grid workshop featured a program committee of over 100 computer scientists that reads like the "Who's Who" of the distributed computing community, selecting 30 papers and 18 posters out of almost 200 submissions. This is for sure one of the highest quality research conferences on Grid computing in the Universe, framed this year by visionaries (and veterans) like Dennis Gannon from Indiana University and his keynote on research challenges for the next generation of Grid systems, and Fran Berman (SDSC), Fabrizio Gagliardi (EGEE, now Microsoft), Carl Kesselman (UCLA/ISI) and Mark Linesch (GGF and HP) on the panel titled "What Will Grids Look Like in Five Years."
The complete article is avaiable at:
Wednesday, November 16, 2005
Some of the links that prompted me to write this blog are:
Keeping an eye on Apple's Grid computing efforts
Microsoft High-Performance Computing Strategy
Platform Computing and IBM Push the Boundaries of Supercomputing Performance
Grid Computing and Clustering -- the next OS battleground
See complete story here: http://news.taborcommunications.com/msgget.jsp?mid=508707
This is a very good development as we will see more collaboration between industry and academia as well as standardization.
Monday, November 14, 2005
Even though the networking requirement of most real grid applications are much more than provided by PERN, a developing country like Pakistan can not afford to have another dedicated high-speed network. So, PERN would be our starting point to any real grid computing implementation in Pakistan.
PERN utilizes the existing Optical Fiber System (OFS) of Pakistan Telecommunication Private Limited (PTCL) and National Telecommunication Limited (NTC) and IP/ATM backbone of NTC is utilized for the core network of PERN. The network design of PERN consists of three nodal points at Islamabad, Lahore and Karachi as shown in figure below. Most educational institutions are connected to their respective nodal point by a 256 Kb/s to 6Mbps link from the nearest exchange of NTC/PTCL using OFS, DXX, DRS or VSAT, whichever is technically feasible.
According to PERN website, the current interconnection of three main nodes is on 34x34 Mbps and Internet connectivity is 65 Mbps for Islamabad, 33 Mbps for Lahore and 57 Mbps for Karachi. This architecture allows institutions to pool resources with each other through national fiber network and to access Internet from the respective nodal points. The bandwidths provisioned and planned through the PERN network for various universities can be found on PERN website.
In order to elaborate the differences between PERN and similar networks of developed countries, the following is the architecture of the United Kingdom National Backbone Research and Education Network (see the figure below). The figure especially shows differences in speed and reliability of the two networks.
Comments on the design, performance and architecture of PERN are welcome as I am in the process of collecting and consolidating views from the industry people on this topic.
Sunday, November 13, 2005
The Sensors, Instrumentation and Radiation Effects (SIRE) research group invites applications for an EPSRC funded studentship with immediate effect.
The SIRE group has a broad research programme in the areas of experimental particle physics, developing detectors, and grid/distributed computing.
The LHC (Large Hadron Collider) in Geneva, Switzerland is about to begin an exciting and cutting edge experiment in the world. It is projected to produce tens of petabytes of data per year from 2007. This huge data will require extensive distributed Grid technologies to analyse and store it (LHC Computing Grid, http://lcg.web.cern.ch/LCG/).
The group is also working on a running experiment at SLAC (Stanford Linear Accelerator Center) called BaBar which is producing and analysing large amount of data on B mesons. Currently, it uses the largest object database in the world (800TB+).
The successful candidate can contribute directly to developing Grid Middleware for the LCG or e-Science projects, working with worldwide expects on Grid Computing at RAL (Rutherford Appleton Lab), CERN in Gevena and SLAC at Stanford University in California. He/she will have a chance to attend short and long term visits at these research labs.
Candidates should have a good honours degree in Physics, Computer Science, or related numerate subject. It would be beneficial to have a keen interest in computing: in particular Java/C++, the Linux operating system and distributed/Grid computing
Applications with a CV and informal inquiries should be directed to:
Dr Akram Khan
Sunday, November 06, 2005
Gartner Inc.'s 2006 Top 10 Strategic Technologies list holds out lots of hope, not just hype, for virtualization and grid computing, among others. Analysts Carl Claunch and David Cearley are predicting these technologies will be mature enough to offer value in the next 18 to 36 months, and that means they should be on your list of technologies to research -- or adopt -- in the coming year.
Lists the following:
- Grid computing
- Service-oriented business applications (SOBAs)
- Pervasive computing
- OLED/LEP technologies
- Location-aware services
- Desktop search tools
- Instant messaging
Tuesday, October 18, 2005
Infrastructure Requirements: The Network
Network is the heart of any successful grid implementation. Most grid implementations are using the high speed fiber optics backbone providing speeds up to 40 Gbps. If the network connectivity is not reliable or appropriate bandwidth is not available, the grid applications deployed on top of it should communicate as little as possible and support high latency, or the deployment will fail. For normal data-intensive or low latency application, high speed fiber optics network should be there.
At present, grids are built on high-performance network. According to Berman et. al., by the year 2002, most of those networks had roughly 10Gbps backbone. Examples of such networks include Abilene Network (USA), SuperJanet backbone (UK), GEANT Network (intra-Europe), APAN (Asia Pacific), and others. A given institution is connected via about 1 Gbps link to the backbone and has around a 100 Mbps LAN. This means that there is a 10:1:0.1 Gbps ratio between national, organizational, desktop links.
A Global Terabit Research Network (GTRN) is expected to enhance this ratio many times. GTRN aims to enhance the international, national, organizational, optical desktop and copper desktop link ratios to 1000:1000:100:10:1 Gbps, a 100 times increase from the current state. The NSF funded TeraGrid project, has one of the most striking network infrastructure with four locations spread across USA linked with a backbone of 40 Gbps.
Hardware Requirements: Shared Resources
Resources are the main building block of the grid. The whole concept was introduced to share resources, so there should be redundant and highly-available resources. Even simple grid systems include a combination of high speed and high capacity data storage in addition to a large amount of computational power. Additionally, a scientific grid consists of specialized analysis, visualization and scientific equipments. Other specialized grids have other components as well.
Software Requirements: The Grid Middleware
The software layer between the operating system and the applications is termed as middleware. It provides a variety of services required by an application to function correctly. Middleware has recently re-emerged as a means of integrating software applications running in distributed heterogeneous environments. Middleware thus refers to the software which is common to multiple applications and builds on the network transport services to enable ready development of new applications and network services. CORBA, for example, defines a middleware standard.
In a grid, the middleware is used to hide the heterogeneous nature and provide users and applications with a homogeneous and seamless environment by providing a set of standardized interfaces to a variety of services . With the use of service oriented architecture in grid computing (see next section for details), this middleware consists of the services commonly used by the grid applications like authentication, resource access and management, etc. Examples of such middleware include the Globus toolkit.
With so many resources available, these need to be looked up by probable users and need to be managed properly. This task is performed by resource managers which manage resources like processing power by distributing it among the many applications depending upon their priority. GRAM, the Globus Resource Allocation Manager is one such resource manager which is an integral part of the Globus toolkit.
Considering that the main purpose of most grid implementations is distributed processing, we also need a meta-scheduler most of the times.
Most of the grids would also require specialized software applications making use of the available grid resources in the most optimal way. These applications are usually built using the services provided by the middleware, resource managers, job schedulers and other components.
Software Requirements: Grid Portals - The User Interface for the Grid
In order to provide easy access to the grid services and the resources, a web portal like interface to grid was introduced called The Grid Portal. Just like a web portal allows users to access various resources via a web interface, a grid portal provides access to grid resources. Grid portal utilizes the web browser as a thin client and thus has the advantage of having minimal setup time on the machines of the users. A typical grid portal provides functionality to authenticate users, permit them to access remote resources, help them make decisions about scheduling jobs, and allow users to access and manipulate grid enabled databases and file systems. Grid portal access can also be personalized by the use of profiles, which are created and stored for each portal user.
Many teams have come up with various applications and projects helpful in the development of the grid portals which include NPACI Hotpage, OGCE, SDSC Grid Port Toolkit, Mississippi Computational Web Portal, Lattice Portal, Grid Portal Development Kit and many others.
Grid Certification Authority
The Grid Security Model as described in Globus Grid Security Infrastructure (GSI) is an extension of public key infrastructure (X.509 certificates). In the short term the user generates his short-term proxy using his long-term certificate. Grid implementations thus require presence of a Certification Authority to issue certificates to users and hosts. Grid Certificates are just like the normal certificates used on the Internet and even the same authorities can be used. But due to security considerations, it is expected that grid has its own certification authorities.
Wednesday, October 12, 2005
Microsoft is creating a "Cluster Compute" version of Windows and intends to work more closely with grid industry standards bodies, Tony Hey, the company's corporate vice president of technical computing, said in an interview with CNET News.com on Tuesday.
Tuesday, October 11, 2005
16-19 May 2006
!!Submission Deadline: 15th November 2005!!
CCGrid 2006 is the sixth in a series of successful international conferences and
for the first time will take place in the heart of South-East Asia ? Singapore.
The conference will be held at Singapore Management University in the centre of
Singapore. The past years have seen tremendous challenges with the convergence
of Web Services and Grid Technology. There have been major initiatives ?
internationally as well as locally ? within the community that has taken up
these challenges. Grid Technology enables us to make a major change in the
paradigm for conducting our work with the holy grail of ?computing on tap?,
which in particular includes collaborative sharing. With this in mind CCGrid 2006
provides researchers and practitioners with an excellent opportunity to share
their research and experience at the cross-roads of Grid Technology. The areas
of interest include, but are not limited to, the following:
? Web Services Flow Languages
? Programming Models, Tools & Environments
? Peer-to-Peer computing
? Information Services
? Resource Exchange Architectures
? Grid-based Problem Solving Environments
? Scientific, Engineering and Commercial Grid Applications
? Middleware for Clusters and Grids
? Parallel File Systems & Wide Area File Systems
? Scheduling and Load Balancing
? Performance Evaluation and Modelling
? Resource Management and Scheduling
? Computational Data and Information Grid
? Architectures and Systems
? Grid Economies and Service Architectures
Authors are invited to submit a full length 8-page paper of double column text
using single spaced 10 pt size type on 8.5?x11? paper, as per IEEE manuscript
guidelines. Detailed paper submission instructions will be placed on the
conference web-page. It is expected that the proceedings will be published by
the IEEE Computer Society Press, USA, and will be made available online through
the IEEE Digital Library.
SPECIAL EVENTS ? WORKSHOPS - TUTORIALS
Those wishing to organise workshops, present tutorials on emerging topics or
participate in the industry track are invited to contact the respective chair
for further information.
Papers Due: 15th November 2005
Camera-Ready Papers: 15th February 2006
Notification of Acceptance: 15th January 2006
Tutorial Proposals: 15th January 2006
Saturday, October 08, 2005
- The Grid: Blueprint for a Future Computing Infrastructure, Morgan Kaufmann, 1998
- The Grid 2: Blueprint for a New Computing Infrastructure, Morgan Kaufmann, 2003
- Grid Computing Making The Global Infrastructure a Reality, John Wiley & Sons, 2003
- Grid Computing - Practical Guide to Technology and Applications, Charles River Media, 2004
- IBM Grid Computing (On Demand Series), Prentice Hall, 2003
Thursday, October 06, 2005
Computational Grid: These grids provide secure access to huge pool of shared processing power suitable for high throughput applications and computation intensive computing.
Data Grid: Data grids provide an infrastructure to support data storage, data discovery, data handling, data publication, and data manipulation of large volumes of data actually stored in various heterogeneous databases and file systems.
Collaboration Grid: With the advent of Internet, there has been an increased demand for better collaboration. Such advanced collaboration is possible using the grid. For instance, persons from different companies in a virtual enterprise can work on different components of a CAD project without even disclosing their proprietary technologies.
Network Grid: A Network Grid provides fault-tolerant and high-performance communication services. Each grid node works as a data router between two communication points, providing data-caching and other facilities to speed up the communications between such points.
Utility Grid: This is the ultimate form of the Grid, in which not only data and computation cycles are shared but software or just about any resource is shared. The main services provided through utility grids are software and special equipments. For instance, the applications can be run on one machine and all the users can send their data to be processed to that machine and receive the result back.
Sunday, October 02, 2005
- High throughput computing
- Distributed Supercomputing
- Data-intensive computing
- On demand computing (utility computing)
- Collaboration within and among organizations
- Data sharing between various offices and partners
- Virtual enterprises and virtual markets could be developed easily using grids
- Providing virtual services, like virtual lectures, virtual stores, etc
- To connect and share heterogeneous distributed resources
Saturday, October 01, 2005
Ian Foster has provided a checklist to identify a grid saying that a grid is one which:
- Coordinates resources not subject to centralized control
- Uses standard, open, general-purpose interfaces and protocols
- Delivers non-trivial qualities of service
Grid computing can be though of as a distributed computing infrastructure that can provide all computing resources as and when required just like the electrical grids and other utility grids do.
Grid computing involves coordinating and sharing computing,data,network resources that are dynamically and geographically dispersed. Resource grid involves utility computing,on-demand and adaptive enterprises Data grid focuses on life-cycle control,distributed file systems and Web services,like google. Compute grid,the most common in use now,Focus on servers and PCs,the most sought after grid. This has been fueling advanced research in science and academia, now entering the corporate world.
Wednesday, September 28, 2005
A Distributed System can be defined as one in which hardware and software components at networked computers communicate and coordinate their activity by sharing resources such as information, data, compute cycles, bandwidth and storage. Examples include the World Wide Web, Clusters, Mobile Computing, Grid Computing, and many others.
Historically, workstations and personal computing systems used to work individually solving smaller problems while supercomputers were used for complex problems. With the increase in the network speeds and storage density, coupled with the availability of high-end computers and communication equipments at reasonable prices, this trend has changed during the last few decades. It is now agreed upon that we are living in an exponential world with transistor count doubling every 18 months (Moore’s Law), storage density doubling every 12 months, and fiber optics speeds doubling every 9 months (see the figure below).
This shows that Network speeds will grow at double the rate of processor speed, thus the case for distributed computing becomes even stronger.
Sunday, September 25, 2005
Ever since the off the shelf networked computers became popular, the interest of people in distributed systems is increasing. Many architectures, strategies and libraries were made. Grid Computing is one such emerging new paradigm for next-generation distributed computing. It enables the sharing, selection, and aggregation of geographically distributed heterogeneous resources.
A number of teams all over the world are working on various aspects of grid computing. This work is an effort to have a research and education grid in Pakistan considering its specific limitations and requirements. It studies the various implementation architectures of grids and based upon the results, proposes Pakistan Research and Education Grid Initiative (PAREGIN). PARAGIN is collaborative grid architecture suitable for Pakistan and provides guidelines for the middleware, network infrastructure and services useful for researchers, students and teachers. The work also includes cost and usability analysis of the services. Based upon the proposal, a prototype grid was implemented along with a smaller set of services.
See complete thesis here.
Saturday, September 24, 2005
You can see the complete version of my thesis here.